The subject of data-driven modeling has been addressed in various disciplinessuch as statistics, pattern recognition, signal processing, genomics, artificial neural networks, machine learning, and data mining, which adopt specialized terminology and conceptual frameworks to motivate various learning algorithms, in spite of the close similarity (equivalence) between actual algorithms. The main commonality between these methodologies is that they all develop algorithms for estimating predictive models from data, albeit providing quite different motivation for these algorithms. This textbook, accessible to undergraduate students and practitioners, emphasizes the methodology and principles of predictive learning, rather than specialized terminology or detailed descriptionof learning algorithms. Introduction to Predictive Learning adopts the conceptual framework developed in Vapnik-Chervonenkis (VC) theory, focusing on the methodological and practical aspects of VC-theory rather than its technical details. Offers a unifying/coherent treatment of learning from data in terms of fundamental underlying concepts. Presents a mixture of mathematical and philosophical concepts related to predictive learning and induction Explains technical aspects of learning methods by means of examples and application studies Provides problems, programming assignments and writing assignments at the end of each chapter. INDICE: Introduction.- Basic Learning Approaches and Complexity Control.- Philosophical Perspective.- Philosophical Interpretation of Predictive Learning.- Inductive Learning and Statistical Learning Theory.- Nonlinear StatisticalMethods.- Neural Network Learning.- Margin-Based Methods and Support Vector Machines.- Combining Methods and Boosting.- Alternative Learning Formulations.-Appendix A: Probability and Statistics.- Appendix B: Linear Algebra.- Index.
- ISBN: 978-1-4419-0258-0
- Editorial: Springer
- Encuadernacion: Cartoné
- Páginas: 400
- Fecha Publicación: 01/06/2010
- Nº Volúmenes: 1
- Idioma: Inglés